© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16043
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.66
    AccessorTable
    -0.60
    EndGlobalSection
    -0.56
    
    -0.56
    IndentedString
    -0.51
    omock
    -0.50
     @"/
    -0.49
     ""],
    -0.49
     HasFactory
    -0.48
    MigrationBuilder
    -0.48
    POSITIVE LOGITS
     étoient
    0.63
     avoient
    0.57
     enfans
    0.55
     dieux
    0.54
     noastră
    0.52
     auroit
    0.52
     vectorielles
    0.52
     étoit
    0.50
    lemény
    0.50
    version
    0.49
    Activations Density 5.680%

    No Known Activations